Peningkatan Pengarahan Beam dan Estimasi Sudut Kedatangan Berbasis CNN untuk Sistem Antena MIMO Cerdas
-
Abdul Karim
*
Program Studi Teknologi Informasi, Fakultas Sain dan Teknologi, Universitas Labuhanbatu, Rantauprapat,
Indonesia
- Iwan Purnama Pasca Sarjana Program Studi Manajemen Pendidikan, Universitas Labuhanbatu, Rantauprapat, Indonesia
- Andi Ernawati Program Studi Teknologi Informasi dan Komunikasi, Sekolah Tinggi Ilmu Kesehatan As Syifa Kisaran, Indonesia
Abstract
This study proposes a Convolutional Neural Network (CNN)–based approach to enhance the intelligence of MIMO antenna systems in Internet of Things (IoT) environments, particularly for modeling the relationship between wireless channel characteristics and achievable communication capacity. Modern MIMO systems face complex challenges due to dynamic channel conditions such as noise, path loss, and multipath fading, which significantly affect data transmission quality. In this research, channel-related features are processed through a structured preprocessing stage before being fed into a CNN model to learn nonlinear relationships among channel parameters. The developed model is designed to predict achievable channel capacity accurately as part of an adaptive and intelligent wireless communication framework. Experimental results show that the proposed CNN model achieves a Test Loss of 0.0317 and a Mean Absolute Error (MAE) of 0.1267 on unseen test data. Visualization of actual versus predicted values indicates that the model demonstrates good generalization across most data ranges, although some deviations remain at extremely high capacity values. Compared to conventional approaches, the CNN-based method shows superior capability in capturing complex correlations among MIMO channel parameters. Therefore, this approach contributes to the development of adaptive and efficient intelligent antenna systems, supporting the growing demands of next-generation IoT communication networks.
References
S. Lavdas, P. K. Gkonis, E. Tsaknaki, L. Sarakis, P. Trakadas, and K. Papadopoulos, “A Deep Learning Framework for Adaptive Beamforming in Massive MIMO Millimeter Wave 5G Multicellular Networks,” Electronics (Switzerland), vol. 12, no. 17, Sep. 2023, doi: 10.3390/electronics12173555.
Y. Huo et al., “Technology trends for massive MIMO towards 6G,” Sensors, vol. 23, no. 13, p. 6062, Jul. 2023, doi: 10.3390/s23136062.
J. Wang, X. Zhang, X. Shi, and J. Song, “Higher spectral efficiency for mmWave MIMO: Enabling techniques and precoder designs,” IEEE Commun. Mag., vol. 59, no. 4, pp. 116–122, Apr. 2021, doi: 10.1109/MCOM.001.2000763.
F. Wen, J. Shi, and Z. Zhang, “Generalized Spatial Smoothing in Bistatic EMVS-MIMO Radar,” Signal Process., vol. 193, p. 108406, Apr. 2021, doi: 10.1016/j.sigpro.2021.108406.
F. Zhao, G. Hu, H. Zhou, and C. Zhan, “CAE-CNN-Based DOA Estimation Method for Low-Elevation-Angle Target,” Remote Sensing 2023, Vol. 15, vol. 15, no. 1, Dec. 2022, doi: 10.3390/rs15010185.
E. Basar, M. Di Renzo, J. De Rosny, M. Debbah, M. S. Alouini, and R. Zhang, “Wireless communications through reconfigurable intelligent surfaces,” IEEE Access, vol. 7, pp. 116753–116773, 2019, doi: 10.1109/ACCESS.2019.2935192.
C. Liaskos, S. Nie, A. Tsioliaridou, A. Pitsillides, S. Ioannidis, and I. Akyildiz, “A new wireless communication paradigm through software-controlled metasurfaces,” IEEE Commun. Mag., vol. 56, no. 9, pp. 162–169, 2018, doi: 10.1109/MCOM.2018.1700659.
Q. Wu and R. Zhang, “Towards smart and reconfigurable environment: Intelligent reflecting surface aided wireless network,” IEEE Commun. Mag., vol. 58, no. 1, pp. 106–112, Jan. 2020, doi: 10.1109/MCOM.001.1900107.
F. Zhao, G. Hu, H. Zhou, and C. Zhan, “CAE-CNN-Based DOA Estimation Method for Low-Elevation-Angle Target,” Remote Sens. (Basel)., vol. 15, no. 1, Jan. 2023, doi: 10.3390/rs15010185.
D. Roy et al., “Going beyond RF: A survey on how AI-enabled multimodal beamforming will shape the NextG standard,” Comput. Netw., vol. 228, p. 109729, Jun. 2023, doi: 10.1016/j.comnet.2023.109729.
S. K. Ibrahim et al., “Design, Challenges and developments for 5G massive MIMO antenna systems at sub 6-GHz band: A Review,” Nanomaterials, vol. 13, no. 3, p. 520, Feb. 2023, doi: 10.3390/nano13030520.
B. S. Khan, S. Jangsher, A. Ahmed, and A. Al-Dweik, “URLLC and eMBB in 5G industrial IoT: A Survey,” IEEE Open J. Commun. Soc., vol. 3, pp. 1134–1163, 2022, doi: 10.1109/OJCOMS.2022.3189013.
C. Bockelmann et al., “Massive machine-type communications in 5G: Physical and MAC-layer solutions,” IEEE Commun. Mag., vol. 54, no. 9, pp. 59–65, Sep. 2016, doi: 10.1109/MCOM.2016.7565189.
P. Dong, H. Zhang, G. Y. Li, I. S. Gaspar, and N. NaderiAlizadeh, “Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems,” IEEE J. Sel. Top. Signal Process., vol. 13, no. 5, pp. 989–1000, Sep. 2019, doi: 10.1109/JSTSP.2019.2925975.
Y. Guo, L. Zhang, J. Zhang, P. Guo, and Z. Chen, “A Coherent Signal Beamforming Technique Based on Sub-Array Cross Correlation,” Digit. Signal Process., vol. 121, p. 103291, Mar. 2022, doi: 10.1016/j.dsp.2021.103291.
A. M. Elbir, K. V. Mishra, S. A. Vorobyov, and R. W. Heath, “Twenty-Five Years of Advances in Beamforming: From convex and nonconvex optimization to learning techniques,” IEEE Signal Process. Mag., vol. 40, no. 4, pp. 118–131, Jun. 2023, doi: 10.1109/MSP.2023.3262366.
R. A. Mucci, “A comparison of efficient beamforming algorithms,” IEEE Trans. Acoust. Speech Signal Process., vol. 32, no. 3, pp. 548–558, 1984, doi: 10.1109/TASSP.1984.1164359.
H. Huang, Y. Peng, J. Yang, W. Xia, and G. Gui, “Fast beamforming design via deep learning,” IEEE Trans. Veh. Technol., vol. 69, no. 1, pp. 1065–1069, Jan. 2019, doi: 10.1109/TVT.2019.2949122.
F. Wen, J. Shi, and Z. Zhang, “Generalized Spatial Smoothing in Bistatic EMVS-MIMO Radar,” Signal Process., vol. 193, p. 108406, Apr. 2021, doi: 10.1016/j.sigpro.2021.108406.
“DOA Estimation in MIMO Radars via Deep Learning - Istanbul Technical University.” Accessed: Feb. 09, 2026. [Online]. Available: https://research.itu.edu.tr/en/publications/doa-estimation-in-mimo-radars-via-deep-learning/?utm_source=chatgpt.com
F. Zhao, G. Hu, H. Zhou, and C. Zhan, “CAE-CNN-Based DOA Estimation Method for Low-Elevation-Angle Target,” Remote Sensing 2023, Vol. 15, vol. 15, no. 1, Dec. 2022, doi: 10.3390/rs15010185.
J. Fuchs, M. Gardill, M. Lubke, A. Dubey, and F. Lurz, “A Machine Learning Perspective on Automotive Radar Direction of Arrival Estimation,” IEEE Access, vol. 10, pp. 6775–6797, 2022, doi: 10.1109/ACCESS.2022.3141587.
W. Cao, W. Ren, Z. Zhang, W. Huang, J. Zou, and G. Liu, “Direction of Arrival Estimation Based on DNN and CNN,” Electronics 2024, Vol. 13, vol. 13, no. 19, Sep. 2024, doi: 10.3390/electronics13193866.
“A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks.” Accessed: Feb. 09, 2026. [Online]. Available: https://www.emergentmind.com/papers/2011.08970
K. Maden and I. Erer, “DOA Estimation in MIMO Radars via Deep Learning,” 2022 30th Telecommunications Forum, TELFOR 2022 - Proceedings, 2022, doi: 10.1109/TELFOR56187.2022.9983686.
S. Unnikrishna Pillai and B. H. Kwon, “Forward/Backward Spatial Smoothing Techniques for Coherent Signal Identification,” IEEE Trans. Acoust. Speech Signal Process., vol. 37, no. 1, pp. 8–15, 1989, doi: 10.1109/29.17496.
F. Zhao, G. Hu, C. Zhan, and Y. Zhang, “DOA estimation method based on improved deep convolutional neural network,” Sensors, vol. 22, no. 4, p. 1305, Feb. 2022, doi: 10.3390/s22041305.
M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation 2023, Vol. 11, vol. 11, no. 3, Mar. 2023, doi: 10.3390/computation11030052.
A. Zafar et al., “Convolutional Neural Networks: A Comprehensive Evaluation and Benchmarking of Pooling Layer Variants,” Symmetry 2024, Vol. 16, vol. 16, no. 11, Nov. 2024, doi: 10.3390/sym16111516.
M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation 2023, Vol. 11, vol. 11, no. 3, Mar. 2023, doi: 10.3390/computation11030052.
R. Raj and A. Kos, “An Extensive Study of Convolutional Neural Networks: Applications in Computer Vision for Improved Robotics Perceptions,” Sensors 2025, Vol. 25, vol. 25, no. 4, Feb. 2025, doi: 10.3390/s25041033.
Copyright (c) 2026 Abdul Karim, Iwan Purnama, Andi Ernawati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the EXPLORER right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in EXPLORER.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in EXPLORER.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
